Özet:

Cardiovascular diseases cause an estimated 17.9 million deaths each year. Early diagnosis and treatment for heart diseases, which make up the vast majority of the total deaths, occupy an important place. Long-standing studies in medicine have made it more successful in the last quarter of the century, thanks to the rapid rise of computer science, by supporting new techniques such as machine learning and artificial intelligence. In this study, machine learning techniques were applied on the sample data set to detect heart disorders and the results were compared. First, the data set was analyzed. It is indicated which data may be found in signs of heart disease. Then a sample model was created using three different machine learning methods and individuals with heart disorders were identified. Compared to the results obtained, Random Forest algorithm observed that it was more successful with a 88% accuracy rate. This was followed by the logistics Regression with a 85% accuracy and the kNN algorithm with a 70% accuracy respectively. The findings show that heart disorders can be easily detected with a few basic data.

Anahtar Kelimeler: